matterport

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to use Membrane to call Matterport APIs (e.g., "membrane action list/run" and "membrane request CONNECTION_ID /path/to/endpoint"), which fetches third‑party Matterport data (user-generated/public content) that the agent will read and can materially change subsequent actions, so it exposes the agent to untrusted third‑party content.